From 2cb3ff88cc6b0cd1e4f2eb96530b1664d4accb6b Mon Sep 17 00:00:00 2001
From: Yejing Lai <yejing.lai@intel.com>
Date: Wed, 5 Aug 2026 10:50:54 +0800
Subject: [PATCH] [BUGFIX][Quant]Fix test_kv_scale_reload failed (#50405)

Signed-off-by: Lai, Yejing <yejing.lai@intel.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
---
 .../schemes/compressed_tensors_w8a16_fp8.py                  | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py
index 23e3510614..144f3ffae9 100644
--- a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py
@@ -137,8 +137,9 @@ class CompressedTensorsW8A16Fp8(CompressedTensorsScheme):
                     "weight_scale",
                     convert_to_channelwise(layer.weight_scale, layer.logical_widths),
                 )
-                self.strategy = QuantizationStrategy.CHANNEL
-                self.weight_quant_key = STRATEGY_TO_WEIGHT_QUANT_KEY[self.strategy]
+                self.weight_quant_key = STRATEGY_TO_WEIGHT_QUANT_KEY[
+                    QuantizationStrategy.CHANNEL
+                ]
                 self.linear_kernel.config.weight_quant_key = self.weight_quant_key
 
             # Canonicalize to (K, N) for the kernel.